SparseDTW: A Novel Approach to Speed up Dynamic Time Warping

TL;DR

SparseDTW is a new space-efficient method for computing the exact Dynamic Time Warping distance by dynamically leveraging similarity between time series, outperforming existing constrained approaches.

Contribution

It introduces a novel, optimal, space-efficient DTW computation method that dynamically exploits data similarity, unlike prior constrained techniques.

Findings

SparseDTW outperforms previous DTW speedup methods.

The approach maintains optimality while reducing space complexity.

Experiments demonstrate improved efficiency in real data scenarios.

Abstract

We present a new space-efficient approach, (SparseDTW), to compute the Dynamic Time Warping (DTW) distance between two time series that always yields the optimal result. This is in contrast to other known approaches which typically sacrifice optimality to attain space efficiency. The main idea behind our approach is to dynamically exploit the existence of similarity and/or correlation between the time series. The more the similarity between the time series the less space required to compute the DTW between them. To the best of our knowledge, all other techniques to speedup DTW, impose apriori constraints and do not exploit similarity characteristics that may be present in the data. We conduct experiments and demonstrate that SparseDTW outperforms previous approaches.